Under the Skin: Backdoor Infection in Multimodal Large Language Models↗ (원문, 새 창)

본문 미리보기

arXiv:2610.24058v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive performance in generating text conditioned on inputs from different modalities. In this work, we introduce backdoor infection, a cross-modal attack framework targeting MLLMs. Starting from a model already injected with a backdoor in one modality, our attack constructs a corresponding trigger in another modality, called the infected modality. Exploiting the model's shared latent spac